Exploiting Machine Learning in Multiscale Modelling of Materials

被引：0
作者：
Anand G. [1 ]
Ghosh S. [2 ]
Zhang L. [3 ]
Anupam A. [4 ]
Freeman C.L. [5 ]
Ortner C. [3 ]
Eisenbach M. [2 ]
Kermode J.R. [6 ]
机构：
[1] Department of Metallurgy and Materials Engineering, Indian Institute of Engineering Science and Technology, Shibpur, Howrah
[2] National Centre for Computational Sciences, Oak Ridge National Laboratory, 1 Bethel Valley Rd, Oak Ridge, 37831, TN
[3] Department of Mathematics, University of British Columbia, 1984 Mathematics Rd, Vancouver, V6T1Z2, BC
[4] Department of Computer Science, Cardiff Metropolitan University, Llandaff Campus, Cardiff
[5] Department of Materials Science and Engineering, University of Sheffield, Mappin St, Sheffield
[6] Warwick Centre for Predictive Modelling, School of Engineering, University of Warwick, Warwick
来源：
Journal of The Institution of Engineers (India): Series D | 2023年 / 104卷 / 02期
基金：
美国能源部;
关键词：
Bayesian networks - Learning algorithms - Machine learning;
D O I：
10.1007/s40033-022-00424-z
中图分类号：
学科分类号：
摘要：
Recent developments in efficient machine learning algorithms have spurred significant interest in the materials community. The inherently complex and multiscale problems in Materials Science and Engineering pose a formidable challenge. The present scenario of machine learning research in Materials Science has a clear lacunae, where efficient algorithms are being developed as a separate endeavour, while such methods are being applied as ‘black-box’ models by others. The present article aims to discuss pertinent issues related to the development and application of machine learning algorithms for various aspects of multiscale materials modelling. The authors present an overview of machine learning of equivariant properties, machine learning-aided statistical mechanics, the incorporation of ab initio approaches in multiscale models of materials processing and application of machine learning in uncertainty quantification. In addition to the above, the applicability of Bayesian approach for multiscale modelling will be discussed. Critical issues related to the multiscale materials modelling are also discussed. © 2022, The Institution of Engineers (India).
引用
收藏
页码：867 / 877
页数：10
相关论文
共 96 条
[41]  
Csillery K., Blum M.G., Gaggiotti O.E., Francois O., Approximate Bayesian computation (abc) in practice, Trends Ecolo. Evol., 25, 7, pp. 410-418, (2010)
[42]  
Guha N., Tan X., Multilevel approximate Bayesian approaches for flows in highly heterogeneous porous media and their applications, J. Comput. Appl. Math., 317, pp. 700-717, (2017)
[43]  
Beaumont M.A., Zhang W., Balding D.J., Approximate Bayesian computation in population genetics, Genetics, 162, 4, pp. 2025-2035, (2002)
[44]  
Behler J., Parrinello M., Generalized neural-network representation of high-dimensional potential-energy surfaces, Phys. Rev. Lett., 98, 14, (2007)
[45]  
Bartok A.P., Payne M.C., Kondor R., Csanyi G., Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons, Phys. Rev. Lett., 104, 13, (2010)
[46]  
Bartok A.P., Kondor R., Csanyi G., On representing chemical environments, Phys. Rev. B, 87, 18, (2013)
[47]  
Grisafi A., Wilkins D.M., Csanyi G., Ceriotti M., Symmetry-adapted machine learning for tensorial properties of atomistic systems, Phys. Rev. Lett., 120, 3, (2018)
[48]  
Thompson A.P., Swiler L.P., Trott C.R., Foiles S.M., Tucker G.J., Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials, J. Comput. Phys., 285, pp. 316-330, (2015)
[49]  
Novoselov I., Yanilkin A., Shapeev A., Podryabinkin E., Moment tensor potentials as a promising tool to study diffusion processes, Comput. Mater. Sci., 164, pp. 46-56, (2019)
[50]  
Shapeev A.V., Moment tensor potentials: a class of systematically improvable interatomic potentials, Multiscale Model. Simul., 14, 3, pp. 1153-1173, (2016)
12345678910